Sign in
An Adaptive Updating Method of Target Network Based on Moment Estimates for Deep Reinforcement Learning.
Miaoping Sun
Zequan Yang
Xunhua Dai
Xiaohong Nian
Hongyun Xiong
Haibo Wang
Published in:
Neural Process. Lett. (2023)
Keyphrases
</>
reinforcement learning
detection method
pairwise
significant improvement
decision trees
high precision
high accuracy
dynamic programming
experimental evaluation
clustering method
prior knowledge
input data
similarity measure
classification accuracy
least squares
objective function
classification method
data sets